all InfoSec news
Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
April 23, 2024, 4:11 a.m. | Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang
cs.CR updates on arXiv.org arxiv.org
Abstract: While diffusion models have recently demonstrated remarkable progress in generating realistic images, privacy risks also arise: published models or APIs could generate training images and thus leak privacy-sensitive training information. In this paper, we reveal a new risk, Shake-to-Leak (S2L), that fine-tuning the pre-trained models with manipulated data can amplify the existing privacy risks. We demonstrate that S2L could occur in various standard fine-tuning strategies for diffusion models, including concept-injection methods (DreamBooth and Textual Inversion) …
amplify arxiv can cs.cr cs.lg diffusion models fine-tuning generative leak privacy privacy risk risk
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Cyber Security Engineer
@ ASSYSTEM | Bridgwater, United Kingdom
Security Analyst
@ Northwestern Memorial Healthcare | Chicago, IL, United States
GRC Analyst
@ Richemont | Shelton, CT, US
Security Specialist
@ Peraton | Government Site, MD, United States
Information Assurance Security Specialist (IASS)
@ OBXtek Inc. | United States
Cyber Security Technology Analyst
@ Airbus | Bengaluru (Airbus)